Shape Analysis Approach towards Assessment of Cleft Lip Repair Outcome

PAUL BAKAKI*, Bruce Richard, ELLA PEREIRA, ARISTIDES TAGALAKIS, Andy Ness, YONGHUAI LIU*

*Corresponding author for this work

Research output: Contribution to journalConference proceeding article (ISSN)peer-review

8 Downloads (Pure)

Abstract

Current methods of assessing the quality of a surgically re-
paired cleft lip rely on humans scoring photographs. This is only practical
for research purposes due to the
resources necessary and is not used in routine audit. It has poor valid-
ity due to human subjectivity and thus low inter-rater reliability. An
automatic method for aesthetic outcome assessment of cleft lip repair
is required. The appearance and shape of the lips constitute the region
of interest for analysis. The mouth borderline and corner points are de-
tected using a bilateral semantic network for real-time segmentation. The
bisector of the line linking the mouth corners is estimated as the vertical
symmetric axis. By splitting the mouth blob into two parts, they are
analyzed for similarity and a numeric score ranging from 1 to 5 is then
generated. Pearson correlation coecient between automatically gener-
ated scores and human-assigned ones serves as a validation metric. A
correlation of about 40% indicates a good agreement between human and
computer-based assessments. However, better automatic scoring correla-
tion of 95:9% exists between the automatically detected mouth regions
and those manually drawn by human experts, the third ground truth set
in scenario two. Our method has the potential to automate an outcome
estimation of the aesthetics of cleft lip repair with human bias reduced,
easy implementation and computational eciency.

Keywords

  • Cleft Lip
  • Aesthetic Assessment
  • Segmentation
  • Symmetry
  • Structural Similarity
  • Correlation coefficient

Fingerprint

Dive into the research topics of 'Shape Analysis Approach towards Assessment of Cleft Lip Repair Outcome'. Together they form a unique fingerprint.

Cite this